SOTAVerified

Sugeno integral generalization applied to improve adaptive image binarization

2020-10-20Information Fusion 2020Code Available0· sign in to hype

Bardozzo Francesco, De La Osa Borja, Horansk{\'a}, L'ubom{\'\i}ra, Fumanal-Idocin Javier, delli Priscoli Mattia, Troiano Luigi, Tagliaferri Roberto, Fernandez Javier, Bustince Humberto

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

Classic adaptive binarization methodologies threshold pixels intensity with re-spect to adjacent pixels exploiting integral images. In turn, integral imagesare generally computed optimally by using the summed-area-table algorithm(SAT). This document presents a new adaptive binarization technique basedon fuzzy integral images. Which, in turn, this technique is supported by anefficient design of a modified SAT for generalized Sugeno fuzzy integrals. Wedefine this methodology as FLAT (Fuzzy Local Adaptive Thresholding). Exper-imental results show that the proposed methodology produced a better imagequality thresholding than well-known global and local thresholding algorithms.We proposed new generalizations of different fuzzy integrals to improve existingresults and reaching an accuracy≈0.94 on a wide dataset. Moreover, due tohigh performances, these new generalized Sugeno fuzzy integrals created ad hocfor adaptive binarization, can be used as tools for grayscale processing and morecomplex real-time thresholding applications.

Tasks

Reproductions